A Scalable and Reliable Message Transport Service for the ATLAS Trigger and Data Acquisition System

被引：0

作者：

Kazarov, Andrei ^{[1
]}

Caprini, Mihai ^{[2
]}

Kolos, Serguei ^{[3
]}

Miotto, Giovanna Lehmann ^{[2
]}

Soloviev, Igor ^{[3
]}

机构：

[1] CERN, Geneva, Switzerland

[2] NIPNE HH, Bucharest, Romania

[3] UCI, Irvine, CA USA

来源：

2014 19TH IEEE-NPSS REAL TIME CONFERENCE (RT) | 2014年

关键词：

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The ATLAS Trigger and Data Acquisition (TDAQ) is a large distributed computing system composed of several thousands of interconnected computers and tens of thousands applications. During a run, TDAQ applications produce a lot of control and information messages with variable rates, addressed to TDAQ operators or to other applications. Reliable, fast and accurate delivery of the messages is important for the functioning of the whole TDAQ system. The Message Transport Service (MTS) provides facilities for the reliable transport, the filtering and the routing of the messages, based on the publish-subscribe-notify communication pattern with content-based message filtering. During the ongoing LHC shutdown, MTS was re-implemented, taking into account important requirements like reliability, scalability and performance, handling of slow subscribers case and also simplicity of the design and the implementation. MTS uses CORBA middleware, a common layer for TDAQ infrastructure, and provides sending/subscribing APIs in the Java and C++ programming languages. The paper presents the design and the implementation details of MTS, as well as the results of performance and scalability tests executed on a computing farm with an amount of workers and working conditions which reproduced a realistic TDAQ environment during ATLAS operations.

引用

页数：4